Speaker attribution in German parliamentary debates with QLoRA-adapted large language models

TL;DR

This paper explores using QLoRA-finetuned Llama 2 models to automate speaker attribution in German parliamentary debates, demonstrating competitive performance and advancing political discourse analysis.

Contribution

It introduces a novel application of QLoRA-adapted Llama 2 models for speaker attribution in German political texts, achieving competitive results in a shared task.

Findings

Achieved competitive performance in speaker attribution tasks.

Demonstrated the potential of large language models for political discourse analysis.

Provided insights into semantic role labeling capabilities.

Abstract

The growing body of political texts opens up new opportunities for rich insights into political dynamics and ideologies but also increases the workload for manual analysis. Automated speaker attribution, which detects who said what to whom in a speech event and is closely related to semantic role labeling, is an important processing step for computational text analysis. We study the potential of the large language model family Llama 2 to automate speaker attribution in German parliamentary debates from 2017-2021. We fine-tune Llama 2 with QLoRA, an efficient training strategy, and observe our approach to achieve competitive performance in the GermEval 2023 Shared Task On Speaker Attribution in German News Articles and Parliamentary Debates. Our results shed light on the capabilities of large language models in automating speaker attribution, revealing a promising avenue for computational analysis of political discourse and the development of semantic role labeling systems.